New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Prp Meta Skill

by Wirasm in Wirasm/prp

Authors, refactors, and consolidates Agent Skills PRP-style.

MITAuto-check passedDevelopment

Install Prp Meta Skill

skills CLI
$ npx skills add Wirasm/prp --skill prp-meta-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Wirasm/prp prp-meta-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Wirasm/prp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/prp-meta-skill .claude/skills/prp-meta-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
prp-meta-skill
GitHub stars
2.3k
Token cost
~1.8k tokens
SKILL.md length
829 words
Files
8 (incl. references)
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

Authors, refactors, and consolidates Agent Skills PRP-style.

  • Works in 4 steps: Context is King — give the agent ALL the… → Validation that fits — workflow skills… → Information dense — real trigger… → …
  • The user wants to create a skill
  • SKILL.md covers Prescribe the craft, not the…, The PRP lens — applied to the…, Step 0 — Pick the mode and Create — quick spine (full…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prp Meta Skill is an agent skill from Wirasm/prp. Authors, refactors, and consolidates Agent Skills PRP-style. Use when the user wants to "create a skill", "write a new skill", "trim a SKILL.md", "split a skill into references", "consolidate workflow skills", "replace duplicated skill logic with composition", redesign a skill workflow, or invokes $prp-meta-skill.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `references/consolidating-workflows.md`, `references/creating-skills.md` and `references/refactoring-skills.md`).

It sits in Development, covering Refactoring and Skill authoring. The repository describes itself as: Prompts, workflows and more for agentic engineering. The licence is MIT.

When your agent uses it

  • The user wants to create a skill
  • Write a new skill
  • Trim a SKILL.md
  • Split a skill into references

Example prompts

  • “create a skill”
  • “write a new skill”
  • “trim a SKILL.md”
  • “/prp-meta-skill”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Context is King — give the agent ALL the context it needs (patterns, gotchas, schemas, examples) via whichever source fits: inline…
  2. Validation that fits — workflow skills ship verifiable gates, and prefer an external, authoritative check (exit code, file presence) over…
  3. Information dense — real trigger phrases, real examples, real file:line. No filler, no restating what the model already knows.
  4. Progressive success — ship the smallest complete SKILL.md that triggers correctly first, validate, then enrich with references. Don't…

What it can do on your machine

Read from SKILL.md and the folder at commit 4352925. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prp Meta Skill loads about 1.8k tokens when it runs, and up to ~9.9k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 829 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~9.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Wirasm/prp at commit 4352925, republished under its MIT licence (© Wirasm). 829 words, ~1,781 tokens.

Download SKILL.mdSave it as .claude/skills/prp-meta-skill/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
prp-meta-skill
description
Authors, refactors, and consolidates Agent Skills PRP-style. Use when the user wants to "create a skill", "write a new skill", "trim a SKILL.md", "split a skill into references", "consolidate workflow skills", "replace duplicated skill logic with composition", redesign a skill workflow, or invokes $prp-meta-skill.

PRP Meta-Skill — Author, Refactor & Consolidate Skills

A PRP-style runbook for three jobs:

  • Create a new skill from scratch (or from an existing command/prompt).
  • Refactor an existing skill — split detail into references/, move output formats into templates/, and trim SKILL.md to a lean spine of pointers.
  • Consolidate overlapping workflows — trace their contracts, choose one composition owner, reuse specialist skills, and retire duplicate paths without losing outcomes or human gates.

This skill is built the way it teaches: a lean body that defers detail to references/. Follow that example.

Prescribe the craft, not the content

This skill is opinionated about how to build a skill well and deliberately agnostic about what any given skill — or the artifact it produces — should contain.

  • Prescribe (firm, universal): progressive disclosure, third-person trigger-rich descriptions, imperative body, no-duplication, lean body, every reference wired, deliberate invocation control, validation that fits. See references/skill-standards.md.
  • Do NOT prescribe (per-project, the author's call): the sections a plan / PRD / report should contain, what a project's template looks like, which phases exist, the domain vocabulary. There is no canonical output shape — guide the author to a good decision, never hand them a fixed one.

Restrictions are not rigidity: be strict on the craft so the author stays free on the content.

The PRP lens — applied to the skill type

Classify the skill first (workflow / artifact-generator / knowledge-reference / tool-wrapper — see references/skill-standards.md → Skill types), then apply only the principles that fit:

  1. Context is King — give the agent ALL the context it needs (patterns, gotchas, schemas, examples) via whichever source fits: inline, bundled and disclosed on demand, pointed to by file path or URL, or gathered from the user at runtime. Curate it — don't dump it. (references/skill-standards.md → Context sources.)
  2. Validation that fits — workflow skills ship verifiable gates, and prefer an external, authoritative check (exit code, file presence) over the agent's own "done" sentinel. A knowledge/reference skill has nothing to validate — don't bolt a loop onto it.
  3. Information dense — real trigger phrases, real examples, real file:line. No filler, no restating what the model already knows.
  4. Progressive success — ship the smallest complete SKILL.md that triggers correctly first, validate, then enrich with references. Don't build all the references before the spine works.

Step 0 — Pick the mode

  • Creating a new skill → follow references/creating-skills.md.
  • Refactoring / trimming an existing skill → follow references/refactoring-skills.md.
  • Consolidating / redesigning overlapping workflow skills → follow references/consolidating-workflows.md.
  • All modes obey the same rules (frontmatter spec, writing style, progressive disclosure, no-duplication, invocation control) → read references/skill-standards.md first.

If the argument is blank, ask which mode and what the skill/target is. Do not guess.

Create — quick spine (full detail in references/creating-skills.md)

  1. Gather context (PRP): collect the concrete phrases that should trigger the skill, the task it performs, the gotchas, and existing patterns to mirror.
  2. Plan resources: what repeats → a scripts/ script; what informs thinking → a references/ doc; what is reused in the output → a templates//assets/ file.
  3. Scaffold: copy templates/SKILL.template.md into .agents/skills/<name>/SKILL.md; create references/, templates/ only as needed.
  4. Write the spine: third-person trigger-rich description; imperative, lean body; push detail to references.
  5. Validate & iterate (references/validation.md): checklist → skill-reviewer → trigger test.
Show full SKILL.md (318 more words)Show less

Refactor — quick spine (full detail in references/refactoring-skills.md)

  1. Inventory the target SKILL.md. Classify each block: spine (keep) vs extractable (output-format templates, schemas, long worked examples, exhaustive pattern catalogs, troubleshooting, edge-case lists).
  2. Extract verbatim into the TARGET skill's own references/ (or templates/ for output formats). Do not reword anything that affects behavior.
  3. Replace with a pointer. For always-needed content (e.g. an output format the agent must always follow), add a mandatory-read instruction: "Before producing output, read templates/<x>.md." For sometimes-needed content, a lazy pointer ("For edge cases, see references/<x>.md").
  4. Behavior-preservation check — the trimmed skill + references must drive the SAME process and SAME output as before. Nothing lost, nothing duplicated.
  5. Validate (references/validation.md).

Consolidate — quick spine (full detail in references/consolidating-workflows.md)

  1. Trace before editing. Inventory inputs, callers, artifacts, side effects, publication, gates, correction paths, and every terminal outcome.
  2. Define the invariant. Preserve the user-visible outcome and authoritative checks; distinguish intentional redesign from accidental regression.
  3. Assign ownership. Give each phase, durable artifact, human decision, and retry loop one maintainer. Compose specialist skills by name instead of copying their instructions.
  4. Design handoffs. Prefer semantic identifiers and complete durable artifacts over remembered filenames, parallel indexes, or lossy summaries. State when to preserve a context and when independence matters.
  5. Remove the old path. Update every caller and public surface, regenerate derived targets, then exercise the new workflow end-to-end.

The single biggest refactor risk: moving an always-needed output format into a lazily-loaded reference, so the agent forgets to read it and the output silently changes. Always pair such extractions with a mandatory-read instruction. See references/refactoring-skills.md.

Resources

  • references/skill-standards.md — frontmatter spec, progressive disclosure, writing style, no-duplication, invocation control, cross-provider notes
  • references/creating-skills.md — full PRP-style create runbook
  • references/refactoring-skills.md — full split-and-trim runbook with a before/after example
  • references/consolidating-workflows.md — workflow trace, ownership, context, publication, correction-loop, and retirement guidance
  • references/validation.md — validation gates, checklist, skill-reviewer, trigger test
  • templates/SKILL.template.md — lean SKILL.md skeleton
  • templates/reference.template.md — skeleton for an extracted reference/template file

© Wirasm, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in .agents/skills/prp-meta-skill of Wirasm/prp.

  • SKILL.md
  • references/consolidating-workflows.md
  • references/creating-skills.md
  • references/refactoring-skills.md
  • references/skill-standards.md
  • references/validation.md
  • templates/SKILL.template.md
  • templates/reference.template.md

Open the folder on GitHubat commit 4352925

Compare with similar skills

Prp Meta Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prp Meta Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prp Meta Skill this skillWirasm/prp2.3k—~1.8kAutomated safety check: PassMIT
Skill Writingmillionco/expect3.6k—~1.8kAutomated safety check: PassCustom licence
Skills Createcoleam00/skills670—~1.6kAutomated safety check: PassMIT
Learning OpportunitiesDrCatHicks/learning-opportunities2.5k—~2.5kAutomated safety check: PassCC-BY-4.0
Build Cs Skillcodestable/CodeStable1.1k—~3kAutomated safety check: PassNone
Skill Creatordkyazzentwatwa/chatgpt-skills114—~444Automated safety check: PassApache-2.0

Similar skills

  • Skill Writing

    millionco/expect

    Write and improve agent skills (SKILL.md files). An agent skill from millionco/expect.

    3.6k GitHub stars~1.8k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed

  • Skills Create

    coleam00/skills

    Author a new Claude Code skill the house way, or refactor a fat skill into a lean SKILL.md + references/.

    670 GitHub stars~1.6k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Learning Opportunities

    DrCatHicks/learning-opportunities

    Facilitates deliberate skill development during AI-assisted coding.

    2.5k GitHub stars~2.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Build Cs Skill

    codestable/CodeStable

    CodeStable skill authoring and evolution protocol. An agent skill from codestable/CodeStable.

    1.1k GitHub stars~3k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Skill Creator

    dkyazzentwatwa/chatgpt-skills

    Create or update agent skills with concise SKILL.md instructions, bundled resources, agent metadata, validation, and packaging.

    114 GitHub stars~444 tokensUpdated 6 mo ago
    Agent WorkflowsAuto-check passed

  • Pstack Skill

    fabricioctelles/skills

    Rigorous engineering orchestrator ported from Lauren Tan's pstack (poteto-mode): reads your task, picks one of 23 playbooks (bug fix, feature, refactoring, perf, investigation, prototype, babysit…

    106 GitHub stars~5k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

More from Wirasm/prp

All 37 skills in this repo

  • PRP Loop

    Wirasm/prp

    Runs the plan, implement and review pipeline detached in fresh headless sessions, looping review and fix until the pull request is clean.

    2.3k GitHub stars~894 tokensUpdated 6 days ago
    Auto-check passed

  • PRP Loop: Autonomous Pipeline

    Wirasm/prp

    Runs a detached, resumable loop that plans, implements, opens a PR, reviews and fixes a feature across headless CLI sessions until the review is clean.

    2.3k GitHub stars~863 tokensUpdated 6 days ago
    Auto-check passed

  • PRP Workstream Orchestrator

    Wirasm/prp

    Coordinates several PRP workstreams in isolated Git worktrees from one session, verifying proof, holding merge gates and sequencing the merges.

    2.3k GitHub stars~3.5k tokensUpdated 6 days ago
    Auto-check passed

  • PRP Implementation Planner

    Wirasm/prp

    Turns a PRD, issue or description into an implementation-ready plan grounded in codebase evidence, adding root-cause analysis for bugs and publishing issue plans back to the issue.

    2.3k GitHub stars~4.1k tokensUpdated 6 days ago
    Auto-check passed

  • PRP Plan

    Wirasm/prp

    Writes an implementation-ready plan for a feature, bug fix, refactor or chore from a PRD, issue or description, grounded in codebase evidence, and can post it back to the source issue.

    2.3k GitHub stars~4k tokensUpdated 6 days ago
    Auto-check passed

  • PRP Spike

    Wirasm/prp

    Settles a feasibility question with the smallest throwaway build that could disprove it, in an isolated worktree, ending in a verdict backed by evidence instead of a PR.

    2.3k GitHub stars~3.8k tokensUpdated 6 days ago
    Auto-check passed

Categories

Questions about Prp Meta Skill

What does Prp Meta Skill do?

Authors, refactors, and consolidates Agent Skills PRP-style. Prp Meta Skill is an agent skill from Wirasm/prp. Authors, refactors, and consolidates Agent Skills PRP-style.

When should I use Prp Meta Skill?

Prp Meta Skill fits situations like: the user wants to create a skill; write a new skill; trim a SKILL.md; split a skill into references.

How do I install Prp Meta Skill in Claude Code?

Run `npx skills add Wirasm/prp --skill prp-meta-skill -a claude-code`. Or copy the skill folder (.agents/skills/prp-meta-skill in Wirasm/prp) into .claude/skills/prp-meta-skill in your project. Claude Code loads it when a task matches its description.

How do I install Prp Meta Skill in Codex?

Run `npx skills add Wirasm/prp --skill prp-meta-skill -a codex`. Or copy the skill folder (.agents/skills/prp-meta-skill in Wirasm/prp) into .agents/skills/prp-meta-skill in your project. Codex loads it when a task matches its description.

Can I use Prp Meta Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Wirasm/prp --skill prp-meta-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prp-meta-skill, .gemini/skills/prp-meta-skill, .github/skills/prp-meta-skill and .opencode/skills/prp-meta-skill in your project.

What does Prp Meta Skill need to run?

SKILL.md names no scripts, command-line tools or credentials: Prp Meta Skill is instructions for the agent only.

Does Prp Meta Skill access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Prp Meta Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Prp Meta Skill use?

Prp Meta Skill is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prp Meta Skill use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.1k tokens, read only when the agent opens those files.

What are the alternatives to Prp Meta Skill?

Skills that share tags, products or a category with Prp Meta Skill: Skill Writing (millionco/expect, 3.6k stars), Skills Create (coleam00/skills, 670 stars), Learning Opportunities (DrCatHicks/learning-opportunities, 2.5k stars) and Build Cs Skill (codestable/CodeStable, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prp Meta Skill?

Wirasm (a GitHub user) maintains it in Wirasm/prp, which has 2,259 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 2, 2026.

Source: Wirasm/prp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.